I will be speaking at the Machine Learning Conference 2017 in Berlin. The topic of my presentation will be the integration of trained Tensorflow Models into a Jave Enterprise Environment. Basically this means the “last 5%” of integration work (that take up 50% of a project’s time budget) to actually ship a working real world server application that performs inference with a trained Tensorflow model. Here is a little abstract of what I aim to cover in my talk:
In many real world scenarios running inference of a trained model in a third party cloud service is not desirable. Especially in an enterprise setting, the customer often wishes more control over the server infrastructure. The project requirements may include custom cloud or other traditional server infrastructure in which an ML solution is to be integrated. Java is still the most widespread platform for enterprise server systems. Adding a new language or framework in such projects is cumbersome and increases risk and cost. In this talk the possibilities to run inference of trained Tensorflow Models in a Java Enterprise Server environment are discussed, together with real world examples of integration into popular server frameworks like Spring and Apache CXF. Different possibilities for deployment and version control of trained models are explored.
The conference has a number of interesting sessions and talks, ranging from hands-on, practical topics, to some theoretical basics to broader talks discussing the “big picture”.
I am very much forward to attending and hope to see you there!